© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 13787
    Prev
    Next
    INDEX
    Explanations

    possessive pronouns used to express ownership or association

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    possessive pronouns/determiners indicating ownership or relationships (e.g., references to someone’s X).

    oai_token-act-pair · gpt-5Triggered by @jyhe0408

    possessive pronouns, especially "my" and related first-person possessive forms.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_16k/average_l0_68
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    vább
    -0.29
     déroule
    -0.29
    katapos
    -0.28
    jalá
    -0.28
     näm
    -0.27
     všetko
    -0.27
    pageNo
    -0.27
     planche
    -0.27
     feroit
    -0.27
     puisqu
    -0.26
    POSITIVE LOGITS
     own
    1.30
     자신의
    0.87
    自己的
    0.86
    ⤹
    0.85
     their
    0.85
     unſer
    0.82
     his
    0.82
    Own
    0.82
    their
    0.81
    [@BOS@]
    0.80
    Activations Density 0.500%

    No Known Activations